Skip to content

Can I run this model on my hardware?

Choose a model, then your GPU or Mac. Each page shows the memory needed at every quantisation, the longest context that fits and an estimated speed. For custom settings use the VRAM calculator.

Llama 3.2 1B

Llama 3.2 3B

Phi-3 mini 3.8B

Qwen2.5 7B

Mistral 7B v0.3

Llama 3.1 8B

Gemma 2 9B

Qwen2.5 14B

Qwen2.5 32B

Mixtral 8x7B (MoE)

Llama 3.1 70B